The Agent Skills Directory

[SAFE]: No security issues were detected. The skill consists entirely of markdown-based instructions and reference materials for SOC 2 compliance advice.
[INDIRECT_PROMPT_INJECTION]: The skill defines workflows for analyzing external data such as vendor SOC 2 reports and security questionnaires. This creates an attack surface for indirect prompt injection if a third-party document contains adversarial instructions. However, the skill lacks dangerous capabilities—such as file system writes, network operations, or shell execution—that would allow for an exploit to cause harm.
[SAFE]: The skill does not include any scripts, third-party dependencies, or remote code downloads. It relies entirely on the model's internal reasoning and the provided reference files.

soc2